© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104957
    Prev
    Next
    INDEX
    Explanations

    country codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     from
    -1.95
     like
    -1.70
     with
    -1.59
     on
    -1.54
     "
    -1.45
     in
    -1.34
     With
    -1.30
     first
    -1.28
    istorante
    -1.26
    ,"
    -1.25
    POSITIVE LOGITS
     entusias
    1.50
     veder
    1.48
     lavable
    1.45
     furia
    1.43
     יכול
    1.38
    镚
    1.37
     adal
    1.37
     simpto
    1.37
    就能
    1.36
     robuste
    1.36
    Activations Density 0.023%

    No Known Activations